Instructions to use Jerboas86/astrone_split_models with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jerboas86/astrone_split_models with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Jerboas86/astrone_split_models",
	filename="medgemma-27b-text-it-UD-IQ1_S-00001-of-00014.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use Jerboas86/astrone_split_models with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jerboas86/astrone_split_models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Jerboas86/astrone_split_models:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Jerboas86/astrone_split_models:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf Jerboas86/astrone_split_models:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Jerboas86/astrone_split_models:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Jerboas86/astrone_split_models:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Jerboas86/astrone_split_models:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Jerboas86/astrone_split_models:Q4_K_M

Use Docker

docker model run hf.co/Jerboas86/astrone_split_models:Q4_K_M

LM Studio
Jan
Ollama
How to use Jerboas86/astrone_split_models with Ollama:
```
ollama run hf.co/Jerboas86/astrone_split_models:Q4_K_M
```

Unsloth Studio new

How to use Jerboas86/astrone_split_models with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Jerboas86/astrone_split_models to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Jerboas86/astrone_split_models to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Jerboas86/astrone_split_models to start chatting

Docker Model Runner
How to use Jerboas86/astrone_split_models with Docker Model Runner:
```
docker model run hf.co/Jerboas86/astrone_split_models:Q4_K_M
```

Lemonade

How to use Jerboas86/astrone_split_models with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Jerboas86/astrone_split_models:Q4_K_M

Run and chat with the model

lemonade run user.astrone_split_models-Q4_K_M

List all available models

lemonade list

Jerboas86 commited on Jun 18, 2025

Commit

069b4d0

unverified ·

1 Parent(s): 45ab45f

[feat] add medgemma 27b

Browse files

Files changed (14) hide show

medgemma-27b-text-it-UD-IQ1_S-00001-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00002-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00003-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00004-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00005-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00006-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00007-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00008-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00009-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00010-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00011-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00012-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00013-of-00014.gguf +3 -0
medgemma-27b-text-it-UD-IQ1_S-00014-of-00014.gguf +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7e7d6499ce3c4813e88eddc33032c7e06e3c9fcc374189405ec0d9abc33ef6
+size 6535360

+version https://git-lfs.github.com/spec/v1
+oid sha256:7202356b9fcd0b0f4eee5b1ad124ee6e746344b44b9a9d859e11dd8fb283f7f0
+size 968884416

+version https://git-lfs.github.com/spec/v1
+oid sha256:9282dcb28b64e341ef852d79b3e2828624ffa4e4c2f8c9545cc8ff676aa40bcf
+size 489482912

+version https://git-lfs.github.com/spec/v1
+oid sha256:5c818af6748c014ead368245a72ec9ce125d465f606077f290bf2e00aacba0e6
+size 467097280

+version https://git-lfs.github.com/spec/v1
+oid sha256:b032f52f4550fa1b0f1b896279290e5f59db2b5040b7b2637e5de6cd1b2303ff
+size 493977664

+version https://git-lfs.github.com/spec/v1
+oid sha256:f7767c751252afc277120cca5dbd55b94560c9ccd4799cc564963f2ede7374b4
+size 506043040

+version https://git-lfs.github.com/spec/v1
+oid sha256:3d335533273c104ef75ac37ec21ea5a9c0d1bddb23eb172879be833144a7681c
+size 509247040

+version https://git-lfs.github.com/spec/v1
+oid sha256:2937198c7583fd0c6ff1ecb525adb786db4ab333b55b5c6456b1968d9a18344f
+size 496366176

+version https://git-lfs.github.com/spec/v1
+oid sha256:9372038e6f73d187f0f331a49ec4926866fe0728d6cf522998ea597eedde5203
+size 510515200

+version https://git-lfs.github.com/spec/v1
+oid sha256:f1421373f075bd1e8b64e3284665a5d2241a3e6436fe3800834ef52deddba796
+size 510837696

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:b7a0b578e5c5bb9bd19824577b5dc9e974dc9f15fa08d156494cbac2b7168755
+size 508473696

+version https://git-lfs.github.com/spec/v1
+oid sha256:127e0bfb94c31d7bc5b569c47de8416640dfab66d6feec671eb23aaa3e4cc71a
+size 509977408

+version https://git-lfs.github.com/spec/v1
+oid sha256:83627caff4ec8089ab450fa3835466bf0c7b33d267339df0eda9b073340974f7
+size 22622528